CN106919674A - A kind of knowledge Q-A system and intelligent search method built based on Wiki semantic networks - Google Patents

A kind of knowledge Q-A system and intelligent search method built based on Wiki semantic networks Download PDF

Info

Publication number
CN106919674A
CN106919674A CN201710094356.XA CN201710094356A CN106919674A CN 106919674 A CN106919674 A CN 106919674A CN 201710094356 A CN201710094356 A CN 201710094356A CN 106919674 A CN106919674 A CN 106919674A
Authority
CN
China
Prior art keywords
retrieval
knowledge
semantic
wiki
theme
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201710094356.XA
Other languages
Chinese (zh)
Inventor
翁衡
林瑞生
陈嘉焕
练文华
周翰
刘子晴
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Hospital of Traditional Chinese Medicine
Original Assignee
Guangdong Hospital of Traditional Chinese Medicine
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangdong Hospital of Traditional Chinese Medicine filed Critical Guangdong Hospital of Traditional Chinese Medicine
Priority to CN201710094356.XA priority Critical patent/CN106919674A/en
Publication of CN106919674A publication Critical patent/CN106919674A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/245Query processing
    • G06F16/2455Query execution
    • G06F16/24564Applying rules; Deductive queries
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/245Query processing
    • G06F16/2452Query translation
    • G06F16/24522Translation of natural language queries to structured queries

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Machine Translation (AREA)

Abstract

The invention discloses a kind of knowledge Q-A system and intelligent search method built based on Wiki semantic networks, it is related to the technical fields such as text semantic analysis, intelligent retrieval and machine learning.The present invention orients the semi-structured text data of crawl by vertical field Wiki, follow predefined ontologies and extract Knowledge Element automatically, and then set up Ontology using deep learning Algorithm for Training and understand model, realize the paradigmatic relation of Knowledge Element and the semantic understanding of derivation relationship.The present invention combines automatic theme reasoning and expertise orientation two advantages of aspect of optimization that machine learning is based on context semantic understanding, reasonable semantic association is returned through to user input term, the retrieval result of matching is expanded and the retrieval result of reasoning, and the definition of combination expertise, effectively improve information retrieval precision and depth, realize knowledge navigation.Suitable for medical science-special topic knowledge mapping, knowledge question and content recommendation system.

Description

A kind of knowledge Q-A system and intelligent search method built based on Wiki semantic networks
Technical field
It is based on the present invention relates to the technical fields such as text semantic analysis, intelligent retrieval and machine learning, more particularly to one kind Knowledge Q-A system and intelligent search method that Wiki semantic networks build.
Background technology
Contemporary society's information content is increased sharply, and medical domain faces the frequent change of knowledge.In face of massive medical knowledge, either Newly entering healthcare practitioners or senior medical expert has professional knowledge query demand higher.Traditional search engine retrieving from The content for covering can not all meet requirement of the specialist medical knowledge retrieval to preciseness, the degree of accuracy and the degree of correlation to retrieval technique.
A kind of effective solution towards professional knowledge query demand is industry field ontology knowledge base.Body, both structure Into association area vocabulary basic terms and its between relation, and explanation these words constituted using these terms and relation The rule of remittance extension.Body is widely used in artificial intelligence, natural language processing and intelligence as the normalized form of knowledge description In energy information system.Ontological concept is applied to ontology knowledge base the tissue of domain-specific knowledge data, is played efficient association and is known Know concept, build knowledge network, and around knowledge concepts and network collection and tissue areas related data, solve domain knowledge The convenience of the relativity problem of retrieval, retrieval result accuracy and knowledge acquisition still depends on the optimization of search method.
The retrieval technique of current main flow is based on the matching of keyword, and retrieval request is sent by user in the form of keyword, Then existing document in matching database, retrieval result is returned by hit condition of key words co-occurrence.It is this complete based on keyword Word or the retrieval mode of part matching do not consider semantic association between word, it is impossible to process synonymous, Ambiguity.Lifting retrieval is accurate A kind of method of rate and recall ratio is to introduce semantic retrieval.Semantic retrieval is a kind of Knowledge based engineering analysis retrieval, generally certainly By statistical model, computational linguistics application on the basis of right language understanding, with reference to artificial intelligence technology and natural language processing Technology, from the information that the angle analysis information resources of semantic understanding are asked with user search, and completes under knowledge connection model Retrieval.Semantic retrieval has carried out the treatment of semantic level for querying condition, shows as semantic extension, reaches precision ratio higher And recall ratio.The essence of semantic retrieval is to carry out semantic processes improvement to conventional retrieval process, is broadly divided into user search word Semantic processes and the semantic processes to database purchase content.
Treatment for user input term is mainly and carries out that term is synonymous and ambiguity extension, then to the inspection after extension Rope word synonym, ambiguity set of words are retrieved again after carrying out the logical combination of retrieval type, thus expand, constrained matching condition, So as to lift returning result accuracy rate.Treatment for data-base content is mainly and first carries out theme, label to data-base content Classification, what is matched with user search word is no longer simple raw text content, but combines theme, label and original The growth data of text.But either which kind of processing method is all simply extended to matching range, the semantic pass being related to Connection rule is to be manually set rather than machine finds automatically, from terms for the treatment of effeciency, process range and speed is constrained, in face of large-scale number According to storehouse and renewal of knowledge frequency industry field high, the hardly possible realization of real-time update of semantic rules;From in terms of improvement degree, Synonym, the matching of ambiguity word are the extending transversely of lexical semantic, and the unrealized semanteme understood expressed by user's keyword, it is impossible to Carry out tacit knowledge discovery or user search intent inference.
The content of the invention
The invention aims to solve shortcoming present in prior art, and the one kind for proposing is based on Wiki semantic nets Knowledge Q-A system and intelligent search method that network builds.
To achieve these goals, present invention employs following technical scheme:
A kind of knowledge Q-A system built based on Wiki semantic networks, it is characterised in that including:
Basic data module, typing, format specification and the hierarchical structure displaying for basic data;
Intelligent processing module, including body theme predefines unit, thematic knowledge unit and relation recognition extracting unit and pushes away Reason rule generating unit.
A kind of above-mentioned knowledge Q-A system built based on Wiki semantic networks, the basic data module includes Wiki Grand attribute definition unit, Wiki Knowledge Elements typing unit and ontology navigation unit, wherein, data based on ontology navigation unit Exposition, be the knowledge meta-directory with strata system, the exercise question that its strata system is defined according to Knowledge Element in typing Rank generation.
A kind of above-mentioned knowledge Q-A system built based on Wiki semantic networks, the intelligent processing module has been used for Into:
The structure of theme reasoning semantic model and optimization;
Model effect is played using model characteristics to be navigated with scene type hierarchical subject;
Similar theme and extension theme bifurcated tree based on semantic reasoning, and the theme defined with expertise are given birth to jointly Into the context of co-text of retrieval/knowledge question;
Provide the user interim customization linguistic context.
The intelligent search method of above-mentioned a kind of knowledge Q-A system built based on Wiki semantic networks, comprising following step Suddenly:
A) predefined searching motif classification is set;
B) user search word is received;
C) semantic understanding is carried out to term;
D) contents semantic retrieval is carried out according to search condition;
E) semantic parsing is carried out to the content results for retrieving;
F) retrieval result and retrieval inference of intention candidate word are returned;
G) user selects corresponding reasoning candidate word to start new round retrieval.
A kind of intelligent search method of above-mentioned knowledge Q-A system built based on Wiki semantic networks, step c) and bag Include following steps:
C1) calculate term and be based on similarity degree and language construction paradigmatic relation, generate synonym/near synonym set;
C2 c1) is connected with logical "or") in synonym/near synonym set generation search condition.
A kind of intelligent search method of above-mentioned knowledge Q-A system built based on Wiki semantic networks, step d) and bag Include following steps:
D1) to c1) in each word carry out similarity mode retrieval, return to hit text sentence;
D2) according to language construction syntagmatic to c1) in each word carry out the context of co-text degree of correlation matching retrieval, return Hit text sentence.
A kind of intelligent search method of above-mentioned knowledge Q-A system built based on Wiki semantic networks, step e) and bag Include following steps:
E1) extract d1) in term polymerization degree of association word higher be " similar theme " result Candidate Set;
E2) extract d2) in retrieval word combination degree of association word higher as " extension theme " result Candidate Set;
A kind of intelligent search method of above-mentioned knowledge Q-A system built based on Wiki semantic networks, step f) and bag Include following steps:
F1) return to d1) and place text summary as " matching ", " approximate match " retrieval result, return d2) it is and affiliated The summary of text is used as " recommendation ", " semantic matches " retrieval result.
F2 e1) is returned) as " similar theme " result in retrieval inference of intention, return to e2) as retrieval inference of intention In " extension theme " result.
A kind of intelligent search method of above-mentioned knowledge Q-A system built based on Wiki semantic networks, step g) and bag Containing following steps:
G1) semantic reasoning candidate word selected by user is used as new term repeat step c1) generation synonym/near synonym collection Close, while including the original term of user input in step b);
G2 c1) is connected with logical "or") in synonym/near synonym set generation retrieval type;
G3) with logical "and" connect g2) generation retrieval type form final retrieval type;
G4) repeat step d) to step g) is satisfied with retrieval result until obtaining.
Beneficial effects of the present invention:The present invention sets up Ontology and understands mould by deep learning Algorithm for Training corpus Ontologies in user input term and storehouse are carried out the semantic understanding of longitudinal polymerization relation and transverse combination relation by type, are returned Back through reasonable semantic association, expand the retrieval result of matching and the retrieval result of reasoning, and combine expertise or artificial fixed The auxiliary of justice, lifts knowledge navigation effect, realizes the medical ontology knowledge base intelligent Search Technique based on semantic reasoning, this hair It is bright to combine automatic theme reasoning and expertise orientation two aspects of optimization that machine learning is based on context semantic understanding Advantage, effectively improve information retrieval precision and depth, realize knowledge navigation.Suitable for medical science-special topic knowledge mapping, know Know question and answer and content recommendation system.
Brief description of the drawings
Fig. 1 is theory diagram of the invention;
Fig. 2 is progressive guiding intelligent search method flow chart of the invention.
Specific embodiment
The technical scheme in the embodiment of the present invention is clearly and completely illustrated below, it is clear that described embodiment Only a part of embodiment of the invention, rather than whole embodiments.
As shown in figure 1, the invention provides a kind of knowledge Q-A system built based on Wiki semantic networks, the knowledge is asked The system of answering includes:
Basic data module, typing, format specification and the hierarchical structure displaying for basic data;
Intelligent processing module, including body theme predefines unit, thematic knowledge unit and relation recognition extracting unit and pushes away Reason rule generating unit.
A kind of above-mentioned knowledge Q-A system built based on Wiki semantic networks, the basic data module includes Wiki Grand attribute definition unit, Wiki Knowledge Elements typing unit and ontology navigation unit, wherein, data based on ontology navigation unit Exposition, be the knowledge meta-directory with strata system, the exercise question that its strata system is defined according to Knowledge Element in typing Rank generation.
A kind of above-mentioned knowledge Q-A system built based on Wiki semantic networks, the intelligent processing module has been used for Into:
The structure of theme reasoning semantic model and optimization;
Model effect is played using model characteristics to be navigated with scene type hierarchical subject;
Similar theme and extension theme bifurcated tree based on semantic reasoning, and the theme defined with expertise are given birth to jointly Into the context of co-text of retrieval/knowledge question;
Provide the user interim customization linguistic context.
As shown in Fig. 2 a kind of intelligent search method of above-mentioned knowledge Q-A system built based on Wiki semantic networks, Comprise the steps of:
A) predefined searching motif classification is set;
B) user search word is received;
C) semantic understanding is carried out to term;
D) contents semantic retrieval is carried out according to search condition;
E) semantic parsing is carried out to the content results for retrieving;
F) retrieval result and retrieval inference of intention candidate word are returned;
G) user selects corresponding reasoning candidate word to start new round retrieval.
A kind of intelligent search method of above-mentioned knowledge Q-A system built based on Wiki semantic networks, step c) and bag Include following steps:
C1) calculate term and be based on similarity degree and language construction paradigmatic relation, generate synonym/near synonym set;
C2 c1) is connected with logical "or") in synonym/near synonym set generation search condition.
A kind of intelligent search method of above-mentioned knowledge Q-A system built based on Wiki semantic networks, step d) and bag Include following steps:
D1) to c1) in each word carry out similarity mode retrieval, return to hit text sentence;
D2) according to language construction syntagmatic to c1) in each word carry out the context of co-text degree of correlation matching retrieval, return Hit text sentence.
A kind of intelligent search method of above-mentioned knowledge Q-A system built based on Wiki semantic networks, step e) and bag Include following steps:
E1) extract d1) in term polymerization degree of association word higher be " similar theme " result Candidate Set;
E2) extract d2) in retrieval word combination degree of association word higher as " extension theme " result Candidate Set;
A kind of intelligent search method of above-mentioned knowledge Q-A system built based on Wiki semantic networks, step f) and bag Include following steps:
F1) return to d1) and place text summary as " matching ", " approximate match " retrieval result, return d2) it is and affiliated The summary of text is used as " recommendation ", " semantic matches " retrieval result.
F2 e1) is returned) as " similar theme " result in retrieval inference of intention, return to e2) as retrieval inference of intention In " extension theme " result.
A kind of intelligent search method of above-mentioned knowledge Q-A system built based on Wiki semantic networks, step g) and bag Containing following steps:
G1) semantic reasoning candidate word selected by user is used as new term repeat step c1) generation synonym/near synonym collection Close, while including the original term of user input in step b);
G2 c1) is connected with logical "or") in synonym/near synonym set generation retrieval type;
G3) with logical "and" connect g2) generation retrieval type form final retrieval type;
G4) repeat step d) to step g) is satisfied with retrieval result until obtaining.
The above, the only present invention preferably specific embodiment, but protection scope of the present invention is not limited thereto, Any one skilled in the art the invention discloses technical scope in, technology according to the present invention scheme and its Inventive concept is subject to equivalent or change, should all be included within the scope of the present invention.

Claims (9)

1. it is a kind of based on Wiki semantic networks build knowledge Q-A system, it is characterised in that including:
Basic data module, typing, format specification and the hierarchical structure displaying for basic data;
Intelligent processing module, including the predefined unit of body theme, thematic knowledge unit and relation recognition extracting unit and reasoning rule Then generation unit.
2. it is according to claim 1 it is a kind of based on Wiki semantic networks build knowledge Q-A system, it is characterised in that institute State basic data module and include the grand attribute definition units of Wiki, Wiki Knowledge Elements typing unit and ontology navigation unit, wherein, this The exposition of data based on body navigation elements, is the knowledge meta-directory with strata system, and its strata system is according to knowing Know the rank generation of the exercise question that unit defines in typing.
3. it is according to claim 1 it is a kind of based on Wiki semantic networks build knowledge Q-A system, it is characterised in that institute Intelligent processing module is stated for completing:
The structure of theme reasoning semantic model and optimization;
Model effect is played using model characteristics to be navigated with scene type hierarchical subject;
Similar theme and extension theme bifurcated tree based on semantic reasoning, and the theme defined with expertise generate inspection jointly The context of co-text of rope/knowledge question;
Provide the user interim customization linguistic context.
4. it is according to claim 1 it is a kind of based on Wiki semantic networks build knowledge Q-A system intelligent retrieval side Method, it is characterised in that comprise the steps of:
A) predefined searching motif classification is set;
B) user search word is received;
C) semantic understanding is carried out to term;
D) contents semantic retrieval is carried out according to search condition;
E) semantic parsing is carried out to the content results for retrieving;
F) retrieval result and retrieval inference of intention candidate word are returned;
G) user selects corresponding reasoning candidate word to start new round retrieval.
5. it is according to claim 4 it is a kind of based on Wiki semantic networks build knowledge Q-A system intelligent retrieval side Method, it is characterised in that step c) and comprise the following steps:
C1) calculate term and be based on similarity degree and language construction paradigmatic relation, generate synonym/near synonym set;
C2 c1) is connected with logical "or") in synonym/near synonym set generation search condition.
6. it is according to claim 4 it is a kind of based on Wiki semantic networks build knowledge Q-A system intelligent retrieval side Method, it is characterised in that step d) and comprise the following steps:
D1) to c1) in each word carry out similarity mode retrieval, return to hit text sentence;
D2) according to language construction syntagmatic to c1) in each word carry out the context of co-text degree of correlation matching retrieval, return hit Text sentence.
7. it is according to claim 4 it is a kind of based on Wiki semantic networks build knowledge Q-A system intelligent retrieval side Method, it is characterised in that step e) and comprise the following steps:
E1) extract d1) in term polymerization degree of association word higher be " similar theme " result Candidate Set;
E2) extract d2) in retrieval word combination degree of association word higher as " extension theme " result Candidate Set.
8. it is according to claim 4 it is a kind of based on Wiki semantic networks build knowledge Q-A system intelligent retrieval side Method, it is characterised in that step f) and comprise the following steps:
F1) return to d1) and place text summary as " matching ", " approximate match " retrieval result, return d2) and affiliated text Summary as " recommendation ", " semantic matches " retrieval result.
F2 e1) is returned) as " similar theme " result in retrieval inference of intention, return to e2) as in retrieval inference of intention " extension theme " result.
9. it is according to claim 3 it is a kind of based on Wiki semantic networks build knowledge Q-A system intelligent retrieval side Method, it is characterised in that step g) and comprise the steps of:
G1) semantic reasoning candidate word selected by user is used as new term repeat step c1) generation synonym/near synonym set, Include the original term of user input in step b) simultaneously;
G2 c1) is connected with logical "or") in synonym/near synonym set generation retrieval type;
G3) with logical "and" connect g2) generation retrieval type form final retrieval type;
G4) repeat step d) to step g) is satisfied with retrieval result until obtaining.
CN201710094356.XA 2017-02-20 2017-02-20 A kind of knowledge Q-A system and intelligent search method built based on Wiki semantic networks Pending CN106919674A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710094356.XA CN106919674A (en) 2017-02-20 2017-02-20 A kind of knowledge Q-A system and intelligent search method built based on Wiki semantic networks

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710094356.XA CN106919674A (en) 2017-02-20 2017-02-20 A kind of knowledge Q-A system and intelligent search method built based on Wiki semantic networks

Publications (1)

Publication Number Publication Date
CN106919674A true CN106919674A (en) 2017-07-04

Family

ID=59454592

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710094356.XA Pending CN106919674A (en) 2017-02-20 2017-02-20 A kind of knowledge Q-A system and intelligent search method built based on Wiki semantic networks

Country Status (1)

Country Link
CN (1) CN106919674A (en)

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107679062A (en) * 2017-07-31 2018-02-09 石河子大学 The method and electronic equipment that a kind of reasoning colony is intended to
CN108108449A (en) * 2017-12-27 2018-06-01 哈尔滨福满科技有限责任公司 A kind of implementation method based on multi-source heterogeneous data question answering system and the system towards medical field
CN108549667A (en) * 2018-03-23 2018-09-18 绍兴诺雷智信息科技有限公司 A kind of semantic retrieving method of structuring engineering design knowledge
CN108897857A (en) * 2018-06-28 2018-11-27 东华大学 The Chinese Text Topic sentence generating method of domain-oriented
CN109918436A (en) * 2019-03-08 2019-06-21 上海一健事信息科技有限公司 A kind of Medical Knowledge management and inquiry system
CN110008326A (en) * 2019-04-01 2019-07-12 苏州思必驰信息科技有限公司 Knowledge abstraction generating method and system in conversational system
CN110532354A (en) * 2019-08-27 2019-12-03 腾讯科技(深圳)有限公司 The search method and device of content
CN111680173A (en) * 2020-05-31 2020-09-18 西南电子技术研究所(中国电子科技集团公司第十研究所) CMR model for uniformly retrieving cross-media information
CN111949855A (en) * 2020-07-31 2020-11-17 国网上海市电力公司 Knowledge map-based engineering technology knowledge retrieval platform and method thereof
CN112559734A (en) * 2019-09-26 2021-03-26 中国科学技术信息研究所 Presentation generation method and device, electronic equipment and computer readable storage medium
CN112836030A (en) * 2021-01-29 2021-05-25 成都视海芯图微电子有限公司 Intelligent dialogue system and method
CN113254588A (en) * 2021-06-02 2021-08-13 竹间智能科技(上海)有限公司 Data searching method and system
CN116089628A (en) * 2023-02-14 2023-05-09 成都市城市建设和自然资源档案馆 City construction and natural resource archive knowledge graph construction method

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1521661A (en) * 2003-01-29 2004-08-18 黄致辉 Method for information retrieval by using natural language processing function
US20160140172A1 (en) * 2013-04-03 2016-05-19 International Business Machines Corporation Method and Apparatus for Optimizing the Evaluation of Semantic Web Queries
CN106383835A (en) * 2016-08-29 2017-02-08 华东师范大学 Natural language knowledge exploration system based on formal semantics reasoning and deep learning

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1521661A (en) * 2003-01-29 2004-08-18 黄致辉 Method for information retrieval by using natural language processing function
US20160140172A1 (en) * 2013-04-03 2016-05-19 International Business Machines Corporation Method and Apparatus for Optimizing the Evaluation of Semantic Web Queries
CN106383835A (en) * 2016-08-29 2017-02-08 华东师范大学 Natural language knowledge exploration system based on formal semantics reasoning and deep learning

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
郭中锋: "智能健康知识问答系统的研究与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
闫晓妍: "基于语义Wiki的知识检索研究", 《图书馆学研究》 *

Cited By (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107679062A (en) * 2017-07-31 2018-02-09 石河子大学 The method and electronic equipment that a kind of reasoning colony is intended to
CN108108449A (en) * 2017-12-27 2018-06-01 哈尔滨福满科技有限责任公司 A kind of implementation method based on multi-source heterogeneous data question answering system and the system towards medical field
CN108549667A (en) * 2018-03-23 2018-09-18 绍兴诺雷智信息科技有限公司 A kind of semantic retrieving method of structuring engineering design knowledge
CN108549667B (en) * 2018-03-23 2022-04-08 绍兴诺雷智信息科技有限公司 Semantic retrieval method for structural engineering design knowledge
CN108897857B (en) * 2018-06-28 2021-08-27 东华大学 Chinese text subject sentence generating method facing field
CN108897857A (en) * 2018-06-28 2018-11-27 东华大学 The Chinese Text Topic sentence generating method of domain-oriented
CN109918436A (en) * 2019-03-08 2019-06-21 上海一健事信息科技有限公司 A kind of Medical Knowledge management and inquiry system
CN109918436B (en) * 2019-03-08 2022-12-20 麦博(上海)健康科技有限公司 Medical knowledge management and query system
CN110008326A (en) * 2019-04-01 2019-07-12 苏州思必驰信息科技有限公司 Knowledge abstraction generating method and system in conversational system
CN110532354B (en) * 2019-08-27 2023-01-06 腾讯科技(深圳)有限公司 Content retrieval method and device
CN110532354A (en) * 2019-08-27 2019-12-03 腾讯科技(深圳)有限公司 The search method and device of content
CN112559734A (en) * 2019-09-26 2021-03-26 中国科学技术信息研究所 Presentation generation method and device, electronic equipment and computer readable storage medium
CN112559734B (en) * 2019-09-26 2023-10-17 中国科学技术信息研究所 Brief report generating method, brief report generating device, electronic equipment and computer readable storage medium
CN111680173A (en) * 2020-05-31 2020-09-18 西南电子技术研究所(中国电子科技集团公司第十研究所) CMR model for uniformly retrieving cross-media information
CN111680173B (en) * 2020-05-31 2024-02-23 西南电子技术研究所(中国电子科技集团公司第十研究所) CMR model for unified searching cross-media information
CN111949855A (en) * 2020-07-31 2020-11-17 国网上海市电力公司 Knowledge map-based engineering technology knowledge retrieval platform and method thereof
CN112836030A (en) * 2021-01-29 2021-05-25 成都视海芯图微电子有限公司 Intelligent dialogue system and method
CN112836030B (en) * 2021-01-29 2023-04-25 成都视海芯图微电子有限公司 Intelligent dialogue system and method
CN113254588A (en) * 2021-06-02 2021-08-13 竹间智能科技(上海)有限公司 Data searching method and system
CN113254588B (en) * 2021-06-02 2023-08-22 竹间智能科技(上海)有限公司 Data searching method and system
CN116089628A (en) * 2023-02-14 2023-05-09 成都市城市建设和自然资源档案馆 City construction and natural resource archive knowledge graph construction method

Similar Documents

Publication Publication Date Title
CN106919674A (en) A kind of knowledge Q-A system and intelligent search method built based on Wiki semantic networks
CN109408627B (en) Question-answering method and system fusing convolutional neural network and cyclic neural network
CN110046240B (en) Target field question-answer pushing method combining keyword retrieval and twin neural network
KR100533810B1 (en) Semi-Automatic Construction Method for Knowledge of Encyclopedia Question Answering System
CN105528437B (en) A kind of question answering system construction method extracted based on structured text knowledge
CN110377715A (en) Reasoning type accurate intelligent answering method based on legal knowledge map
CN111563149B (en) Entity linking method for Chinese knowledge map question-answering system
CN105868313A (en) Mapping knowledge domain questioning and answering system and method based on template matching technique
US20140032574A1 (en) Natural language understanding using brain-like approach: semantic engine using brain-like approach (sebla) derives semantics of words and sentences
CN106446162A (en) Orient field self body intelligence library article search method
CN113761890B (en) Multi-level semantic information retrieval method based on BERT context awareness
Xiong et al. Knowledge graph question answering with semantic oriented fusion model
CN106776548A (en) A kind of method and apparatus of the Similarity Measure of text
CN111768869B (en) Medical guide mapping construction search system and method for intelligent question-answering system
CN110765755A (en) Semantic similarity feature extraction method based on double selection gates
Megala et al. Enriching text summarization using fuzzy logic
CN110516145B (en) Information searching method based on sentence vector coding
CN112328773A (en) Knowledge graph-based question and answer implementation method and system
Ribeiro et al. Combining analogy with language models for knowledge extraction
CN113590779B (en) Construction method of intelligent question-answering system of knowledge graph in air traffic control field
Maryamah et al. Query Expansion Based on Wikipedia Word Embedding and BabelNet Method for Searching Arabic Documents.
Subiksha Improvement in analyzing healthcare systems using deep learning architecture
CN112417170B (en) Relationship linking method for incomplete knowledge graph
Khin et al. Query classification based information retrieval system
CN116737911A (en) Deep learning-based hypertension question-answering method and system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20170704